No article text was recorded for this version.
gradient accumulation
Version 1 of 132 papers34 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources
- Blog: THUMT: An Open-Source Toolkit for Neural Machine Translation
- Blog: An Inverse-Free and Scalable Sparse Bayesian Extreme Learning Machine for Classification Problems
- Blog: Research on fine tuning parameter insulator identification based on YOLOV4 algorithm
- Blog: e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce
- Blog: Parallel Training for Deep Stacking Networks
- Blog: Recall@k Surrogate Loss with Large Batches and Similarity Mixup
- Blog: Multivariate Dense Retrieval: A Reproducibility Study under a Memory-limited Setup
- Blog: Opacus: User-Friendly Differential Privacy Library in PyTorch
- Blog: Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs
- Blog: Multi-representation ensembles and delayed SGD updates improve syntax-based NMT
- Blog: CIC-NLP at GenAI Detection Task 1: Leveraging DistilBERT for Detecting Machine-Generated Text in English
- Blog: Cramming Protein Language Model Training in 24 GPU Hours
- Blog: Scaling Neural Machine Translation
- Blog: Universal Mini-Batch Consistency for Set Encoding Functions
- Blog: The University of Cambridge's Machine Translation Systems for WMT18
- Blog: PyLate: Flexible Training and Retrieval for Late Interaction Models
- Blog: SGCAST: symmetric graph convolutional auto-encoder for scalable and accurate study of spatial transcriptomics
- Blog: Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation
- Blog: Newton Methods for Convolutional Neural Networks
- Blog: Learning With Average Precision: Training Image Retrieval With a Listwise Loss
- Blog: BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
- Blog: The MLLP-UPV Supervised Machine Translation Systems for WMT19 News Translation Task
- Blog: The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018
- Blog: Batch size invariant Adam
- Blog: Tackling the curse of dimensionality with physics-informed neural networks
- Blog: Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute
- Blog: End-to-End Video Captioning
- Blog: Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance
- Blog: CVIT-MT Systems for WAT-2018
- Blog: Dual-Encoders for Extreme Multi-label Classification
- Blog: A Study on Energy Consumption in AI-Driven Medical Image Segmentation
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_accumulation_6929aced,
title = {gradient accumulation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-accumulation/rdr_6929aced458f439d853b704dfda2b0b0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_gradient_accumulation_6929aced_v1,
title = {gradient accumulation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-accumulation/rdr_6929aced458f439d853b704dfda2b0b0/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}